def prepare_data(self):
"Called to initialize data. Use the call to construct features"
args = self.hparams
for mode in ["train", "dev", "test"]:
cached_features_file = self._feature_file(mode)
if not os.path.exists(cached_features_file):
logger.info("Creating features from dataset file at %s",
args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(
examples,
self.labels,
args.max_seq_length,
self.tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
cls_token=self.tokenizer.cls_token,
cls_token_segment_id=2
if args.model_type in ["xlnet"] else 0,
sep_token=self.tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
pad_on_left=bool(args.model_type in ["xlnet"]),
pad_token=self.tokenizer.convert_tokens_to_ids(
[self.tokenizer.pad_token])[0],
pad_token_segment_id=4
if args.model_type in ["xlnet"] else 0,
pad_token_label_id=self.pad_token_label_id,
)
logger.info("Saving features into cached file %s",
cached_features_file)
torch.save(features, cached_features_file)
def load_and_cache_examples(tokenizer, labels):
examples = read_examples_from_file('./', mode='test')
features = convert_examples_to_features(
examples,
labels,
128,
tokenizer,
cls_token=tokenizer.cls_token,
cls_token_segment_id=0,
sep_token=tokenizer.sep_token,
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0])
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features],
dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features],
dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features],
dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features],
dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_label_ids)
return dataset
def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode):
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args.data_dir,
"cached_{}_{}_{}".format(
mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length)),
)
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info("Loading features from cached file %s",
cached_features_file)
features = torch.load(cached_features_file)
else:
logger.info("Creating features from dataset file at %s", args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(args.model_type in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.pad_token_id,
pad_token_segment_id=tokenizer.pad_token_type_id,
pad_token_label_id=pad_token_label_id,
)
if args.local_rank in [-1, 0]:
logger.info("Saving features into cached file %s",
cached_features_file)
torch.save(features, cached_features_file)
if args.local_rank == 0 and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features],
dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features],
dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features],
dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features],
dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_label_ids)
return dataset
def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode):
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args.data_dir, "cached_{}_{}_{}".format(
mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length)))
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info("Loading features from cached file %s",
cached_features_file)
features = torch.load(cached_features_file)
else:
logger.info("Creating features from dataset file at %s", args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=False,
cls_token=tokenizer.cls_token,
cls_token_segment_id=0,
sep_token=tokenizer.sep_token,
sep_token_extra=False,
pad_on_left=False,
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token
])[0],
pad_token_segment_id=0,
pad_token_label_id=pad_token_label_id)
if args.local_rank in [-1, 0]:
logger.info("Saving features into cached file %s",
cached_features_file)
torch.save(features, cached_features_file)
if args.local_rank == 0 and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features],
dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features],
dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features],
dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features],
dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_label_ids)
return dataset
def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id,
batch_size, mode):
drop_remainder = True if args["tpu"] or mode == "train" else False
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args["data_dir"],
"cached_{}_{}_{}.tf_record".format(
mode,
list(filter(None, args["model_name_or_path"].split("/"))).pop(),
str(args["max_seq_length"])),
)
if os.path.exists(cached_features_file) and not args["overwrite_cache"]:
logging.info("Loading features from cached file %s",
cached_features_file)
dataset, size = load_cache(cached_features_file,
args["max_seq_length"])
else:
logging.info("Creating features from dataset file at %s",
args["data_dir"])
examples = read_examples_from_file(args["data_dir"], mode)
features = convert_examples_to_features(
examples,
labels,
args["max_seq_length"],
tokenizer,
cls_token_at_end=bool(args["model_type"] in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args["model_type"] in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args["model_type"] in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(args["model_type"] in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token
])[0],
pad_token_segment_id=4 if args["model_type"] in ["xlnet"] else 0,
pad_token_label_id=pad_token_label_id,
)
logging.info("Saving features into cached file %s",
cached_features_file)
save_cache(features, cached_features_file)
dataset, size = load_cache(cached_features_file,
args["max_seq_length"])
if mode == "train":
dataset = dataset.repeat()
dataset = dataset.shuffle(buffer_size=8192, seed=args["seed"])
dataset = dataset.batch(batch_size, drop_remainder)
dataset = dataset.prefetch(buffer_size=batch_size)
return dataset, size
def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, lang, mode):
data_path = os.path.join(args.data_dir, lang)
# Load data features from cache or dataset file
cached_features_file = os.path.join(data_path, "cached_{}_{}_{}".format(mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(), str(args.max_seq_length)))
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info("Loading features from cached file %s.", cached_features_file)
features = torch.load(cached_features_file)
else:
logger.info("Creating features from dataset file at %s", data_path)
examples = read_examples_from_file(data_path, mode)
features = convert_examples_to_features(examples, labels, args.max_seq_length, tokenizer,
cls_token_at_end=False,
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=0,
sep_token=tokenizer.sep_token,
sep_token_extra=False,
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=False,
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
pad_token_segment_id=0,
pad_token_label_id=pad_token_label_id
)
logger.info("Saving features into cached file %s", cached_features_file)
torch.save(features, cached_features_file)
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features], dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids)
return dataset
def evaluate(args, model, tokenizer, labels, pad_token_label_id, mode, prefix=""):
#eval_dataset = load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode=mode)
args.eval_batch_size = args.per_gpu_eval_batch_size * max(1, args.n_gpu)
# multi-gpu evaluate
if args.n_gpu > 1:
model = torch.nn.DataParallel(model)
# Eval!
logger.info("***** Running evaluation %s *****", prefix)
logger.info(" Batch size = %d", args.eval_batch_size)
eval_loss = 0.0
nb_eval_steps = 0
preds = None
out_label_ids = None
model.eval()
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Load data features from cache or dataset file
logger.info("Creating features from dataset file at %s", args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
print(len(examples))
print(examples[0]) # list of words in one document (sentence)
out_label_listX=[]
preds_listX=[]
for example in tqdm(examples, desc="Evaluating"):
max_length = 500
min_context = 128
l = len(example.words) #TODO number of segments for each word? word_tokens = tokenizer.tokenize(word)
word_tokens_lengths=[len(tokenizer.tokenize(word)) for word in example.words]
ws=windows(word_tokens_lengths, max_length, min_context)
print(ws)
text_examples=[]
for start_all, start_content, end_content, end_all in ws:
ex=InputExample(guid=example.guid, words=example.words[start_all:end_all], labels=example.labels[start_all:end_all])
text_examples.append(ex)
# przed tym trzeba podzielić
features = convert_examples_to_features(
text_examples,
labels,
512, #args.max_seq_length,
tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(args.model_type in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
pad_token_label_id=pad_token_label_id,
)
if args.local_rank == 0 and not evaluate:
torch.distributed.barrier() # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features], dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features], dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features], dtype=torch.long)
eval_dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids, all_label_ids)
# Note that DistributedSampler samples randomly
eval_sampler = SequentialSampler(eval_dataset) if args.local_rank == -1 else DistributedSampler(eval_dataset)
eval_dataloader = DataLoader(eval_dataset, sampler=eval_sampler, batch_size=args.eval_batch_size)
# Eval!
logger.info(" Num examples = %d", len(eval_dataset))
# batch = next(iter(eval_dataloader))
a = []
b = []
for batch, (start_all, start_content, end_content, end_all) in tqdm(zip(eval_dataloader, ws), desc="Evaluating"):
preds = None
out_label_ids = None
batch = tuple(t.to(args.device) for t in batch)
with torch.no_grad():
inputs = {"input_ids": batch[0], "attention_mask": batch[1], "labels": batch[3]}
if args.model_type != "distilbert":
inputs["token_type_ids"] = (
batch[2] if args.model_type in ["bert", "xlnet"] else None
) # XLM and RoBERTa don"t use segment_ids
outputs = model(**inputs)
tmp_eval_loss, logits = outputs[:2]
if args.n_gpu > 1:
tmp_eval_loss = tmp_eval_loss.mean() # mean() to average on multi-gpu parallel evaluating
eval_loss += tmp_eval_loss.item()
nb_eval_steps += 1
if preds is None:
preds = logits.detach().cpu().numpy()
out_label_ids = inputs["labels"].detach().cpu().numpy()
else:
preds = np.append(preds, logits.detach().cpu().numpy(), axis=0)
out_label_ids = np.append(out_label_ids, inputs["labels"].detach().cpu().numpy(), axis=0)
preds = np.argmax(preds, axis=2)
label_map = {i: label for i, label in enumerate(labels)}
out_label_list = [[] for _ in range(out_label_ids.shape[0])]
preds_list = [[] for _ in range(out_label_ids.shape[0])]
for i in range(out_label_ids.shape[0]):
for j in range(out_label_ids.shape[1]):
if out_label_ids[i, j] != pad_token_label_id:
out_label_list[i].append(label_map[out_label_ids[i][j]])
preds_list[i].append(label_map[preds[i][j]])
#join
for i in range(len(out_label_list)):
a.extend(out_label_list[i][start_content-start_all:end_content-start_all])
b.extend(preds_list[i][start_content-start_all:end_content-start_all])
out_label_listX.append(a)
preds_listX.append(b)
# results = {
# "loss": eval_loss,
# "precision": precision_score(out_label_list, preds_list),
# "recall": recall_score(out_label_list, preds_list),
# "f1": f1_score(out_label_list, preds_list),
# }
eval_loss = eval_loss / nb_eval_steps
try:
results = {
"loss": eval_loss,
"precision": precision_score(out_label_listX, preds_listX),
"recall": recall_score(out_label_listX, preds_listX),
"f1": f1_score(out_label_listX, preds_listX),
}
logger.info("***** Eval results %s *****", prefix)
for key in sorted(results.keys()):
logger.info(" %s = %s", key, str(results[key]))
return results, preds_listX
except IndexError: #no output labels in file
return {}, preds_listX
num_labels=num_labels,
id2label={str(i): label
for i, label in enumerate(labels)},
label2id=label2id,
cache_dir=args.cache_dir if args.cache_dir else None,
)
model = AutoModelForTokenClassification.from_pretrained(
args.model_name_or_path)
model.load_state_dict(
torch.load(os.path.join(args.model_name_or_path, 'pytorch_model.bin'),
map_location='cpu'))
model.to(device)
pad_token_label_id = CrossEntropyLoss().ignore_index
examples = read_examples_from_file(args.data_dir, mode)
features, all_tokens = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
pad_on_left=bool(args.model_type in ["xlnet"]),
pad_token=tokenizer.pad_token_id,
pad_token_segment_id=tokenizer.pad_token_type_id,
pad_token_label_id=pad_token_label_id,
model_dir = 'model/'
model = model_class.from_pretrained(model_dir)
case = False
tokenizer = tokenizer_class.from_pretrained(model_dir, do_lower_case=case)
device = 'cpu'
model.to(device)
# setting the folder for possible whole directory tagging
files_dir = 'data/'
# getting labels
labels = get_labels('labels.txt')
pad_token_label_id = CrossEntropyLoss().ignore_index
# reading examples
examples = read_examples_from_file('.', 'test')
features = convert_examples_to_features(
examples,
labels,
256,
tokenizer,
cls_token_at_end=False,
cls_token=tokenizer.cls_token,
cls_token_segment_id=0,
sep_token=tokenizer.sep_token,
sep_token_extra=False,
pad_on_left=False,
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
pad_token_segment_id=0,
pad_token_label_id=pad_token_label_id)
all_input_ids = torch.tensor([f.input_ids for f in features], dtype=torch.long)
def load_and_cache_examples(args,
tokenizer,
labels,
pad_token_label_id,
lang,
mode,
plain_text=False):
data_path = os.path.join(args.data_dir, lang)
# Load data features from cache or dataset file
cached_features_file = os.path.join(
data_path, "cached_{}_{}_{}".format(
mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length)))
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info("Loading features from cached file %s. Plain text: %s",
cached_features_file, plain_text)
features = torch.load(cached_features_file)
else:
logger.info(
"Creating features from dataset file at %s. Plain text: %s",
data_path, plain_text)
examples = read_examples_from_file(data_path, mode)
features = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=False,
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=0,
sep_token=tokenizer.sep_token,
sep_token_extra=False,
pad_on_left=False,
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token
])[0],
pad_token_segment_id=0,
pad_token_label_id=pad_token_label_id)
logger.info("Saving features into cached file %s",
cached_features_file)
torch.save(features, cached_features_file)
# Convert to Tensors and build dataset
all_input_ids = torch.tensor([f.input_ids for f in features],
dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features],
dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features],
dtype=torch.long)
if not plain_text:
all_label_ids = torch.tensor([f.label_ids for f in features],
dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_label_ids)
return dataset
else:
# assert lang in args.src_langs and lang != args.tgt_lang
language_id = args.src_langs.index(
lang) if lang in args.src_langs else len(args.src_langs)
all_language_id = torch.tensor([language_id] * len(features),
dtype=torch.long)
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_language_id)
return dataset
def load_and_cache_examples(args, task, tokenizer, labels, pad_token_label_id,
mode):
args.data_dir = args.base_data_dir + task.lower()
try:
# print("old args.data_dir: ", args.data_dir, flush=True)
args.data_dir = args.data_dir.replace('/home/rizwan/.flair/datasets/',
'/local/rizwan/UDTree/')
# print("new args.data_dir: ", args.data_dir, flush=True)
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args.data_dir,
"cached_{}_{}_{}".format(
mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length)),
)
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info('-' * 120)
logger.info("Loading features from cached file %s",
cached_features_file)
features = torch.load(cached_features_file)
logger.info('-' * 120)
else:
logger.info("Creating features from dataset file at %s",
args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(args.model_type in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids(
[tokenizer.pad_token])[0],
pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
pad_token_label_id=pad_token_label_id,
)
if args.local_rank in [-1, 0]:
logger.info("Saving features into cached file %s",
cached_features_file)
torch.save(features, cached_features_file)
if args.local_rank == 0 and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Data Shepley debug
if args.data_size and mode == "train":
if args.data_size < len(features):
logger.info('-' * 50)
logger.info(
f'originial data size: {len(features)} truncated to {args.data_size}'
)
features = np.random.choice(features,
args.data_size,
replace=False)
logger.info('-' * 50)
# Convert to Tensors and build dataset
logger.info("- Creating Tensors")
all_input_ids = torch.tensor([f.input_ids for f in features],
dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features],
dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features],
dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features],
dtype=torch.long)
logger.info("- Creating Tensor dataset")
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_label_ids)
random_init_result = None
return dataset, random_init_result, all_label_ids.shape[0]
except:
print("could not print args.data_dir", flush=True)
if args.local_rank not in [-1, 0] and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Load data features from cache or dataset file
cached_features_file = os.path.join(
args.data_dir,
"cached_{}_{}_{}".format(
mode,
list(filter(None, args.model_name_or_path.split("/"))).pop(),
str(args.max_seq_length)),
)
if os.path.exists(cached_features_file) and not args.overwrite_cache:
logger.info('-' * 120)
logger.info("Loading features from cached file %s",
cached_features_file)
features = torch.load(cached_features_file)
logger.info('-' * 120)
else:
logger.info("Creating features from dataset file at %s",
args.data_dir)
examples = read_examples_from_file(args.data_dir, mode)
features = convert_examples_to_features(
examples,
labels,
args.max_seq_length,
tokenizer,
cls_token_at_end=bool(args.model_type in ["xlnet"]),
# xlnet has a cls token at the end
cls_token=tokenizer.cls_token,
cls_token_segment_id=2 if args.model_type in ["xlnet"] else 0,
sep_token=tokenizer.sep_token,
sep_token_extra=bool(args.model_type in ["roberta"]),
# roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
pad_on_left=bool(args.model_type in ["xlnet"]),
# pad on the left for xlnet
pad_token=tokenizer.convert_tokens_to_ids(
[tokenizer.pad_token])[0],
pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
pad_token_label_id=pad_token_label_id,
)
if args.local_rank in [-1, 0]:
logger.info("Saving features into cached file %s",
cached_features_file)
torch.save(features, cached_features_file)
if args.local_rank == 0 and not evaluate:
torch.distributed.barrier(
) # Make sure only the first process in distributed training process the dataset, and the others will use the cache
# Data Shepley debug
if args.data_size and mode == "train":
if args.data_size < len(features):
logger.info('-' * 50)
logger.info(
f'originial data size: {len(features)} truncated to {args.data_size}'
)
features = np.random.choice(features,
args.data_size,
replace=False)
logger.info('-' * 50)
# Convert to Tensors and build dataset
logger.info("- Creating Tensors")
all_input_ids = torch.tensor([f.input_ids for f in features],
dtype=torch.long)
all_input_mask = torch.tensor([f.input_mask for f in features],
dtype=torch.long)
all_segment_ids = torch.tensor([f.segment_ids for f in features],
dtype=torch.long)
all_label_ids = torch.tensor([f.label_ids for f in features],
dtype=torch.long)
logger.info("- Creating Tensor dataset")
dataset = TensorDataset(all_input_ids, all_input_mask, all_segment_ids,
all_label_ids)
random_init_result = None
return dataset, random_init_result, all_label_ids.shape[0]
def main():
parser = argparse.ArgumentParser()
## Required parameters
parser.add_argument(
"--data_dir",
default=None,
type=str,
required=True,
help=
"The input data dir. Should contain files named train, dev, and test.")
parser.add_argument("--model_type",
default=None,
type=str,
required=True,
help="Model type selected in the list: " +
", ".join(MODEL_CLASSES.keys()))
parser.add_argument(
"--model_name_or_path",
default=None,
type=str,
required=True,
help="Path to pre-trained model or shortcut name selected in the list: "
+ ", ".join(ALL_MODELS))
parser.add_argument(
"--output_dir",
default=None,
type=str,
required=True,
help=
"The output directory where the model predictions and checkpoints will be written."
)
## Other parameters
parser.add_argument(
"--sample_type",
default="conll",
type=str,
help=
"raw sample type, conll for standard two column style, cluener for json type"
)
parser.add_argument(
"--labels",
default="",
type=str,
help=
"Path to a file containing all labels. If not specified, CoNLL-2003 labels are used."
)
parser.add_argument(
"--config_name",
default="",
type=str,
help="Pretrained config name or path if not the same as model_name")
parser.add_argument(
"--tokenizer_name",
default="",
type=str,
help="Pretrained tokenizer name or path if not the same as model_name")
parser.add_argument(
"--cache_dir",
default="",
type=str,
help=
"Where do you want to store the pre-trained models downloaded from s3")
parser.add_argument(
"--max_seq_length",
default=128,
type=int,
help=
"The maximum total input sequence length after tokenization. Sequences longer "
"than this will be truncated, sequences shorter will be padded.")
parser.add_argument("--do_train",
action="store_true",
help="Whether to run training.")
parser.add_argument("--do_eval",
action="store_true",
help="Whether to run eval on the dev set.")
parser.add_argument("--do_predict",
action="store_true",
help="Whether to run predictions on the test set.")
parser.add_argument(
"--evaluate_during_training",
action="store_true",
help="Whether to run evaluation during training at each logging step.")
parser.add_argument(
"--do_lower_case",
action="store_true",
help="Set this flag if you are using an uncased model.")
parser.add_argument("--per_gpu_train_batch_size",
default=8,
type=int,
help="Batch size per GPU/CPU for training.")
parser.add_argument("--per_gpu_eval_batch_size",
default=8,
type=int,
help="Batch size per GPU/CPU for evaluation.")
parser.add_argument(
"--gradient_accumulation_steps",
type=int,
default=1,
help=
"Number of updates steps to accumulate before performing a backward/update pass."
)
parser.add_argument("--learning_rate",
default=5e-5,
type=float,
help="The initial learning rate for Adam.")
parser.add_argument("--weight_decay",
default=0.0,
type=float,
help="Weight decay if we apply some.")
parser.add_argument("--adam_epsilon",
default=1e-8,
type=float,
help="Epsilon for Adam optimizer.")
parser.add_argument("--max_grad_norm",
default=1.0,
type=float,
help="Max gradient norm.")
parser.add_argument("--num_train_epochs",
default=3.0,
type=float,
help="Total number of training epochs to perform.")
parser.add_argument(
"--max_steps",
default=-1,
type=int,
help=
"If > 0: set total number of training steps to perform. Override num_train_epochs."
)
parser.add_argument("--warmup_steps",
default=0,
type=int,
help="Linear warmup over warmup_steps.")
parser.add_argument("--logging_steps",
type=int,
default=50,
help="Log every X updates steps.")
parser.add_argument("--save_steps",
type=int,
default=50,
help="Save checkpoint every X updates steps.")
parser.add_argument(
"--eval_all_checkpoints",
action="store_true",
help=
"Evaluate all checkpoints starting with the same prefix as model_name ending and ending with step number"
)
parser.add_argument("--no_cuda",
action="store_true",
help="Avoid using CUDA when available")
parser.add_argument("--overwrite_output_dir",
action="store_true",
help="Overwrite the content of the output directory")
parser.add_argument(
"--overwrite_cache",
action="store_true",
help="Overwrite the cached training and evaluation sets")
parser.add_argument("--seed",
type=int,
default=42,
help="random seed for initialization")
parser.add_argument(
"--fp16",
action="store_true",
help=
"Whether to use 16-bit (mixed) precision (through NVIDIA apex) instead of 32-bit"
)
parser.add_argument(
"--fp16_opt_level",
type=str,
default="O1",
help=
"For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
"See details at https://nvidia.github.io/apex/amp.html")
parser.add_argument("--local_rank",
type=int,
default=-1,
help="For distributed training: local_rank")
parser.add_argument("--server_ip",
type=str,
default="",
help="For distant debugging.")
parser.add_argument("--server_port",
type=str,
default="",
help="For distant debugging.")
args = parser.parse_args()
if os.path.exists(args.output_dir) and os.listdir(
args.output_dir
) and args.do_train and not args.overwrite_output_dir:
raise ValueError(
"Output directory ({}) already exists and is not empty. Use --overwrite_output_dir to overcome."
.format(args.output_dir))
# Setup distant debugging if needed
if args.server_ip and args.server_port:
# Distant debugging - see https://code.visualstudio.com/docs/python/debugging#_attach-to-a-local-script
import ptvsd
print("Waiting for debugger attach")
ptvsd.enable_attach(address=(args.server_ip, args.server_port),
redirect_output=True)
ptvsd.wait_for_attach()
# Setup CUDA, GPU & distributed training
if args.local_rank == -1 or args.no_cuda:
device = torch.device("cuda" if torch.cuda.is_available()
and not args.no_cuda else "cpu")
args.n_gpu = torch.cuda.device_count()
else: # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
torch.cuda.set_device(args.local_rank)
device = torch.device("cuda", args.local_rank)
torch.distributed.init_process_group(backend="nccl")
args.n_gpu = 1
args.device = device
# Setup logging
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
level=logging.INFO if args.local_rank in [-1, 0] else logging.WARN)
logger.warning(
"Process rank: %s, device: %s, n_gpu: %s, distributed training: %s, 16-bits training: %s",
args.local_rank, device, args.n_gpu, bool(args.local_rank != -1),
args.fp16)
# Set seed
set_seed(args)
# Prepare CONLL-2003 task
labels = get_labels(args.labels)
num_labels = len(labels)
# Use cross entropy ignore index as padding label id so that only real label ids contribute to the loss later
pad_token_label_id = CrossEntropyLoss().ignore_index
# Load pretrained model and tokenizer
if args.local_rank not in [-1, 0]:
torch.distributed.barrier(
) # Make sure only the first process in distributed training will download model & vocab
args.model_type = args.model_type.lower()
config_class, model_class, tokenizer_class = MODEL_CLASSES[args.model_type]
config = config_class.from_pretrained(
args.config_name if args.config_name else args.model_name_or_path,
num_labels=num_labels)
tokenizer = tokenizer_class.from_pretrained(
args.tokenizer_name
if args.tokenizer_name else args.model_name_or_path,
do_lower_case=args.do_lower_case)
model = model_class.from_pretrained(
args.model_name_or_path,
from_tf=bool(".ckpt" in args.model_name_or_path),
config=config)
if args.local_rank == 0:
torch.distributed.barrier(
) # Make sure only the first process in distributed training will download model & vocab
model.to(args.device)
logger.info("Training/evaluation parameters %s", args)
# Training
if args.do_train:
train_dataset = load_and_cache_examples(args,
tokenizer,
labels,
pad_token_label_id,
mode="train")
global_step, tr_loss = train(args, train_dataset, model, tokenizer,
labels, pad_token_label_id)
logger.info(" global_step = %s, average loss = %s", global_step,
tr_loss)
# Saving best-practices: if you use defaults names for the model, you can reload it using from_pretrained()
if args.do_train and (args.local_rank == -1
or torch.distributed.get_rank() == 0):
# Create output directory if needed
if not os.path.exists(args.output_dir) and args.local_rank in [-1, 0]:
os.makedirs(args.output_dir)
logger.info("Saving model checkpoint to %s", args.output_dir)
# Save a trained model, configuration and tokenizer using `save_pretrained()`.
# They can then be reloaded using `from_pretrained()`
model_to_save = model.module if hasattr(
model,
"module") else model # Take care of distributed/parallel training
model_to_save.save_pretrained(args.output_dir)
tokenizer.save_pretrained(args.output_dir)
# Good practice: save your training arguments together with the trained model
torch.save(args, os.path.join(args.output_dir, "training_args.bin"))
# Evaluation
results = {}
if args.do_eval and args.local_rank in [-1, 0]:
tokenizer = tokenizer_class.from_pretrained(
args.output_dir, do_lower_case=args.do_lower_case)
checkpoints = [args.output_dir]
if args.eval_all_checkpoints:
checkpoints = list(
os.path.dirname(c) for c in sorted(
glob.glob(args.output_dir + "/**/" + WEIGHTS_NAME,
recursive=True)))
logging.getLogger("pytorch_transformers.modeling_utils").setLevel(
logging.WARN) # Reduce logging
logger.info("Evaluate the following checkpoints: %s", checkpoints)
for checkpoint in checkpoints:
global_step = checkpoint.split(
"-")[-1] if len(checkpoints) > 1 else ""
model = model_class.from_pretrained(checkpoint)
model.to(args.device)
result, _ = evaluate(args,
model,
tokenizer,
labels,
pad_token_label_id,
mode="dev",
prefix=global_step)
if global_step:
result = {
"{}_{}".format(global_step, k): v
for k, v in result.items()
}
results.update(result)
output_eval_file = os.path.join(args.output_dir, "eval_results.txt")
with open(output_eval_file, "w") as writer:
for key in sorted(results.keys()):
writer.write("{} = {}\n".format(key, str(results[key])))
if args.do_predict and args.local_rank in [-1, 0]:
tokenizer = tokenizer_class.from_pretrained(
args.output_dir, do_lower_case=args.do_lower_case)
model = model_class.from_pretrained(args.output_dir)
model.to(args.device)
result, predictions = evaluate(args,
model,
tokenizer,
labels,
pad_token_label_id,
mode="test")
# Save results
output_test_results_file = os.path.join(args.output_dir,
"test_results.txt")
with open(output_test_results_file, "w") as writer:
for key in sorted(result.keys()):
writer.write("{} = {}\n".format(key, str(result[key])))
# Save predictions
output_test_predictions_file = os.path.join(args.output_dir,
"test_predictions.txt")
with open(output_test_predictions_file, "w") as writer:
if args.sample_type == 'conll':
testdataset = read_examples_from_file(args.data_dir, 'test')
elif args.sample_type == 'cluener':
testdataset = read_cluener_example_from_file(
args.data_dir, 'test')
example_id = 0
for data in testdataset:
for word in data.words:
if predictions[example_id]:
output_line = word + " " + predictions[example_id].pop(
0) + "\n"
writer.write(output_line)
else:
logger.warning(
"Maximum sequence length exceeded: No prediction for '%s'.",
word)
example_id += 1
return results
